From e9028b0ff2bad1954568604dc17725692c8524d6 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Thu, 23 Mar 2006 02:59:20 -0800 Subject: [PATCH] [PATCH] fix scheduler deadlock We have noticed lockups during boot when stress testing kexec on ppc64. Two cpus would deadlock in scheduler code trying to grab already taken spinlocks. The double_rq_lock code uses the address of the runqueue to order the taking of multiple locks. This address is a per cpu variable: if (rq1 < rq2) { spin_lock(&rq1->lock); spin_lock(&rq2->lock); } else { spin_lock(&rq2->lock); spin_lock(&rq1->lock); } On the other hand, the code in wake_sleeping_dependent uses the cpu id order to grab locks: for_each_cpu_mask(i, sibling_map) spin_lock(&cpu_rq(i)->lock); This means we rely on the address of per cpu data increasing as cpu ids increase. While this will be true for the generic percpu implementation it may not be true for arch specific implementations. One way to solve this is to always take runqueues in cpu id order. To do this we add a cpu variable to the runqueue and check it in the double runqueue locking functions. Signed-off-by: Anton Blanchard Acked-by: Ingo Molnar Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 6b6e0d70eb..a5bd60453e 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -237,6 +237,7 @@ struct runqueue { task_t *migration_thread; struct list_head migration_queue; + int cpu; #endif #ifdef CONFIG_SCHEDSTATS @@ -1654,6 +1655,9 @@ unsigned long nr_iowait(void) /* * double_rq_lock - safely lock two runqueues * + * We must take them in cpu order to match code in + * dependent_sleeper and wake_dependent_sleeper. + * * Note this does not disable interrupts like task_rq_lock, * you need to do so manually before calling. */ @@ -1665,7 +1669,7 @@ static void double_rq_lock(runqueue_t *rq1, runqueue_t *rq2) spin_lock(&rq1->lock); __acquire(rq2->lock); /* Fake it out ;) */ } else { - if (rq1 < rq2) { + if (rq1->cpu < rq2->cpu) { spin_lock(&rq1->lock); spin_lock(&rq2->lock); } else { @@ -1701,7 +1705,7 @@ static void double_lock_balance(runqueue_t *this_rq, runqueue_t *busiest) __acquires(this_rq->lock) { if (unlikely(!spin_trylock(&busiest->lock))) { - if (busiest < this_rq) { + if (busiest->cpu < this_rq->cpu) { spin_unlock(&this_rq->lock); spin_lock(&busiest->lock); spin_lock(&this_rq->lock); @@ -6029,6 +6033,7 @@ void __init sched_init(void) rq->push_cpu = 0; rq->migration_thread = NULL; INIT_LIST_HEAD(&rq->migration_queue); + rq->cpu = i; #endif atomic_set(&rq->nr_iowait, 0); -- 2.39.5